alvis/AgapHost
1
0
Fork 0
Code Issues 1 Pull Requests Actions Packages Projects Releases Wiki Activity

openai: OpenClaw plugins, memory migration tooling, backup and GPU scripts

Browse Source 
Plugins for the Adolf gateway:
  - hindsight-openclaw-plugin: expanded memory recall/retain surface for the
    Cognee -> Hindsight migration
  - todoist-capture-plugin: posts captured ideas to agap-mcp's /capture-idea,
    sending the kb#180 bearer token when AGAP_MCP_TOKEN is present
  - feedback-loop-openclaw-plugin, kimi-quota-footer-plugin, cognee-mcp,
    cognee-openclaw-plugin

Plus migrate-adolf-memory-banks.mjs for the memory-bank split,
backup-hindsight-adolf.sh / backup-llm-dbs.sh (the Hindsight and adolf-state
backups that were previously missing), and gpu_preload_check.sh for the
GTX 1070 residency checks.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
alvis
2026-07-30 04:41:53 +00:00
parent b27d31b3ca
commit f67a5bee67
21 changed files with 4735 additions and 101 deletions
Download Patch File Download Diff File Expand all files Collapse all files

23
openai/cognee-mcp/Dockerfile Normal file
View File

@@ -0,0 +1,23 @@
# Adolf kb#70 — cognee-mcp deletion fix.
#
# Base: official upstream image (do not hand-roll cognee-mcp itself).
# Patches exactly two files to fix a real bug: the `forget` MCP tool (the
# only deletion-capable tool actually exposed to agents — `delete`,
# `delete_dataset`, and `prune` exist in src/server.py but are never
# registered with @mcp.tool(), so they're unreachable dead code) never
# exposed a `data_id` parameter, and its cognee_client.forget() wrapper
# never forwarded one either — even though cognee's own /api/v1/forget
# endpoint has always supported single-item deletion via dataset+data_id.
# Net effect: agents could delete an entire dataset but never a single
# entry/fact. Verified 2026-07-07 by calling the live /api/v1/forget
# endpoint directly with data_id — entry-level delete works fine
# server-side; the MCP bridge was just never wired up to use it.
#
# See src/cognee_client.py forget() and src/server.py forget() for the
# fix. Both files are full copies of the upstream 0.5.4 source with only
# the forget-related code changed (diff against the base image at
# /app/src/{cognee_client,server}.py to see the exact delta).
FROM cognee/cognee-mcp:1.2.2
COPY src/cognee_client.py /app/src/cognee_client.py
COPY src/server.py /app/src/server.py

629
openai/cognee-mcp/src/cognee_client.py Normal file
View File

@@ -0,0 +1,629 @@
"""
Cognee Client abstraction that supports both direct function calls and HTTP API calls.
This module provides a unified interface for interacting with Cognee, supporting:
- Direct mode: Directly imports and calls cognee functions (default behavior)
- API mode: Makes HTTP requests to a running Cognee FastAPI server
"""
import sys
import hashlib
from typing import Optional, Any, List, Dict
from uuid import UUID
from contextlib import redirect_stdout
import httpx
from cognee.shared.logging_utils import get_logger
import json
try:
from .server_utils import normalize_delete_mode
except ImportError:
from server_utils import normalize_delete_mode
try:
from .retrieval_utils import get_chunk_neighbors_from_graph, get_document_from_graph
except ImportError:
from retrieval_utils import get_chunk_neighbors_from_graph, get_document_from_graph
logger = get_logger()
class CogneeClient:
"""
Unified client for interacting with Cognee via direct calls or HTTP API.
Parameters
----------
api_url : str, optional
Base URL of the Cognee API server (e.g., "http://localhost:8000").
If None, uses direct cognee function calls.
api_token : str, optional
Authentication token for the API (optional, required if API has authentication enabled).
"""
def __init__(self, api_url: Optional[str] = None, api_token: Optional[str] = None):
self.api_url = api_url.rstrip("/") if api_url else None
self.api_token = api_token
self.use_api = bool(api_url)
# Extract tenant ID from tenant URL pattern: tenant-<uuid>.*.cognee.ai
self.tenant_id: Optional[str] = None
if self.api_url:
import re
match = re.search(r"tenant-([0-9a-f-]{36})", self.api_url)
if match:
self.tenant_id = match.group(1)
if self.use_api:
logger.info(f"Cognee client initialized in API mode: {self.api_url}")
if self.tenant_id:
logger.info(f"Tenant ID extracted from URL: {self.tenant_id}")
self.client = httpx.AsyncClient(timeout=300.0) # 5 minute timeout for long operations
else:
logger.info("Cognee client initialized in direct mode")
# Import cognee only if we're using direct mode
import cognee as _cognee
self.cognee = _cognee
def _get_headers(self, include_content_type: bool = True) -> Dict[str, str]:
"""Get headers for API requests.
Uses X-Api-Key + X-Tenant-Id for tenant APIs (cloud),
falls back to Bearer token for local/self-hosted backends.
"""
headers: Dict[str, str] = {}
if include_content_type:
headers["Content-Type"] = "application/json"
if self.api_token:
if self.tenant_id:
headers["X-Api-Key"] = self.api_token
headers["X-Tenant-Id"] = self.tenant_id
else:
headers["Authorization"] = f"Bearer {self.api_token}"
return headers
@staticmethod
def _json_or_success(response: httpx.Response) -> Dict[str, Any]:
"""Return a JSON body when present, otherwise a generic success shape."""
if not response.content:
return {"status": "success"}
try:
parsed = response.json()
except ValueError:
return {"status": "success", "message": response.text}
if isinstance(parsed, dict):
return parsed
return {"status": "success", "result": parsed}
@staticmethod
def _text_upload(data: Any) -> Dict[str, tuple[str, str, str]]:
"""Create a content-addressed text upload for API-mode ingestion."""
content = str(data)
digest = hashlib.md5(content.encode("utf-8")).hexdigest()
return {"data": (f"text_{digest}.txt", content, "text/plain")}
async def add(
self, data: Any, dataset_name: str = "main_dataset", node_set: Optional[List[str]] = None
) -> Dict[str, Any]:
"""
Add data to Cognee for processing.
Parameters
----------
data : Any
Data to add (text, file path, etc.)
dataset_name : str
Name of the dataset to add data to
node_set : List[str], optional
List of node identifiers for graph organization
Returns
-------
Dict[str, Any]
Result of the add operation
"""
if self.use_api:
endpoint = f"{self.api_url}/api/v1/add"
files = self._text_upload(data)
form_data = {
"datasetName": dataset_name,
}
if node_set is not None:
form_data["node_set"] = json.dumps(node_set)
response = await self.client.post(
endpoint,
files=files,
data=form_data,
headers=self._get_headers(include_content_type=False),
)
response.raise_for_status()
return response.json()
else:
with redirect_stdout(sys.stderr):
await self.cognee.add(data, dataset_name=dataset_name, node_set=node_set)
return {"status": "success", "message": "Data added successfully"}
async def cognify(
self,
datasets: Optional[List[str]] = None,
custom_prompt: Optional[str] = None,
graph_model: Any = None,
) -> Dict[str, Any]:
"""
Transform data into a knowledge graph.
Parameters
----------
datasets : List[str], optional
List of dataset names to process
custom_prompt : str, optional
Custom prompt for entity extraction
graph_model : Any, optional
Custom graph model (only used in direct mode)
Returns
-------
Dict[str, Any]
Result of the cognify operation
"""
if self.use_api:
# API mode: Make HTTP request
endpoint = f"{self.api_url}/api/v1/cognify"
payload = {
"datasets": datasets or ["main_dataset"],
"run_in_background": False,
}
if custom_prompt:
payload["custom_prompt"] = custom_prompt
response = await self.client.post(endpoint, json=payload, headers=self._get_headers())
response.raise_for_status()
return response.json()
else:
# Direct mode: Call cognee directly
with redirect_stdout(sys.stderr):
kwargs = {}
if datasets:
kwargs["datasets"] = datasets
if custom_prompt:
kwargs["custom_prompt"] = custom_prompt
if graph_model:
kwargs["graph_model"] = graph_model
await self.cognee.cognify(**kwargs)
return {"status": "success", "message": "Cognify completed successfully"}
async def search(
self,
query_text: str,
query_type: str,
datasets: Optional[List[str]] = None,
system_prompt: Optional[str] = None,
top_k: int = 15,
) -> Any:
"""
Search the knowledge graph.
Parameters
----------
query_text : str
The search query
query_type : str
Type of search (e.g., "GRAPH_COMPLETION", "INSIGHTS", etc.)
datasets : List[str], optional
List of datasets to search
system_prompt : str, optional
System prompt for completion searches
top_k : int
Maximum number of results
Returns
-------
Any
Search results
"""
if self.use_api:
# API mode: Make HTTP request
endpoint = f"{self.api_url}/api/v1/search"
payload = {"query": query_text, "search_type": query_type.upper(), "top_k": top_k}
if datasets:
payload["datasets"] = datasets
if system_prompt:
payload["system_prompt"] = system_prompt
response = await self.client.post(endpoint, json=payload, headers=self._get_headers())
response.raise_for_status()
return response.json()
else:
# Direct mode: Call cognee directly
from cognee.modules.search.types import SearchType
with redirect_stdout(sys.stderr):
search_kwargs = {
"query_type": SearchType[query_type.upper()],
"query_text": query_text,
"top_k": top_k,
}
if datasets:
search_kwargs["datasets"] = datasets
if system_prompt:
search_kwargs["system_prompt"] = system_prompt
results = await self.cognee.search(**search_kwargs)
return results
async def delete(self, data_id: UUID, dataset_id: UUID, mode: str = "soft") -> Dict[str, Any]:
"""
Delete data from a dataset.
Parameters
----------
data_id : UUID
ID of the data to delete
dataset_id : UUID
ID of the dataset containing the data
Returns
-------
Dict[str, Any]
Result of the deletion
"""
normalized_mode = normalize_delete_mode(mode)
if self.use_api:
# The deprecated delete endpoint still carries the mode contract.
# Fall back to the datasets endpoint for older backends that removed it.
endpoint = f"{self.api_url}/api/v1/delete"
response = await self.client.delete(
endpoint,
params={
"data_id": str(data_id),
"dataset_id": str(dataset_id),
"mode": normalized_mode,
},
headers=self._get_headers(),
)
if response.status_code in {404, 405}:
endpoint = f"{self.api_url}/api/v1/datasets/{str(dataset_id)}/data/{str(data_id)}"
response = await self.client.delete(endpoint, headers=self._get_headers())
response.raise_for_status()
return self._json_or_success(response)
else:
# Direct mode: Call cognee directly
from cognee.modules.users.methods import get_default_user
with redirect_stdout(sys.stderr):
user = await get_default_user()
result = await self.cognee.datasets.delete_data(
dataset_id=dataset_id,
data_id=data_id,
mode=normalized_mode,
user=user,
)
return result or {"status": "success"}
async def prune_data(self) -> Dict[str, Any]:
"""
Prune all data from the knowledge graph.
Returns
-------
Dict[str, Any]
Result of the prune operation
"""
if self.use_api:
# Note: The API doesn't expose a prune endpoint, so we'll need to handle this
# For now, raise an error
raise NotImplementedError("Prune operation is not available via API")
else:
# Direct mode: Call cognee directly
with redirect_stdout(sys.stderr):
await self.cognee.prune.prune_data()
return {"status": "success", "message": "Data pruned successfully"}
async def prune_system(self, metadata: bool = True) -> Dict[str, Any]:
"""
Prune system data from the knowledge graph.
Parameters
----------
metadata : bool
Whether to prune metadata
Returns
-------
Dict[str, Any]
Result of the prune operation
"""
if self.use_api:
# Note: The API doesn't expose a prune endpoint
raise NotImplementedError("Prune system operation is not available via API")
else:
# Direct mode: Call cognee directly
with redirect_stdout(sys.stderr):
await self.cognee.prune.prune_system(metadata=metadata)
return {"status": "success", "message": "System pruned successfully"}
async def get_pipeline_status(
self, dataset_ids: List[UUID], pipeline_name: str
) -> Dict[str, Any]:
"""
Get the status of a pipeline run.
Parameters
----------
dataset_ids : List[UUID]
List of dataset IDs
pipeline_name : str
Name of the pipeline
Returns
-------
Dict[str, Any]
Status information keyed by dataset ID
"""
if self.use_api:
# API mode: query the server's dataset-status endpoint, which
# reports the pipeline run state keyed by dataset id.
endpoint = f"{self.api_url}/api/v1/datasets/status"
params = [("dataset", str(d)) for d in dataset_ids]
response = await self.client.get(endpoint, params=params, headers=self._get_headers())
response.raise_for_status()
return response.json()
else:
# Direct mode: Call cognee directly
from cognee.modules.pipelines.operations.get_pipeline_status import get_pipeline_status
with redirect_stdout(sys.stderr):
status = await get_pipeline_status(dataset_ids, pipeline_name)
return status
async def list_datasets(self) -> List[Dict[str, Any]]:
"""
List all datasets.
Returns
-------
List[Dict[str, Any]]
List of datasets
"""
if self.use_api:
# API mode: Make HTTP request
endpoint = f"{self.api_url}/api/v1/datasets"
response = await self.client.get(endpoint, headers=self._get_headers())
response.raise_for_status()
return response.json()
else:
# Direct mode: Call cognee directly
from cognee.modules.users.methods import get_default_user
from cognee.modules.data.methods import get_datasets
with redirect_stdout(sys.stderr):
user = await get_default_user()
datasets = await get_datasets(user.id)
return [
{"id": str(d.id), "name": d.name, "created_at": str(d.created_at)}
for d in datasets
]
async def get_document(
self,
document_id: str,
include_metadata: bool = True,
max_chunks: int = 0,
) -> Dict[str, Any]:
"""Retrieve a full document with its chunks from the graph database."""
if self.use_api:
raise NotImplementedError("get_document is not available in API mode")
from cognee.infrastructure.databases.unified import get_unified_engine
with redirect_stdout(sys.stderr):
unified = await get_unified_engine()
return await get_document_from_graph(
unified.graph,
document_id,
include_metadata=include_metadata,
max_chunks=max_chunks,
)
async def get_chunk_neighbors(
self,
chunk_id: str,
neighbor_count: int = 2,
include_target: bool = True,
direction: str = "both",
) -> Dict[str, Any]:
"""Retrieve neighboring chunks around a target chunk from its parent document."""
if self.use_api:
raise NotImplementedError("get_chunk_neighbors is not available in API mode")
from cognee.infrastructure.databases.unified import get_unified_engine
with redirect_stdout(sys.stderr):
unified = await get_unified_engine()
return await get_chunk_neighbors_from_graph(
unified.graph,
chunk_id,
neighbor_count=neighbor_count,
include_target=include_target,
direction=direction,
)
# -- V2 API methods -----------------------------------------------------
async def remember(
self,
data: Any,
dataset_name: str = "main_dataset",
session_id: Optional[str] = None,
custom_prompt: Optional[str] = None,
) -> Dict[str, Any]:
"""Store data in memory via remember().
With session_id: stores in session cache only (fast).
Without session_id: full add + cognify pipeline (permanent).
"""
if self.use_api:
if session_id:
if custom_prompt:
logger.warning(
"remember: custom_prompt is not supported with session_id in API mode "
"(the /remember/entry endpoint does not forward custom_prompt)"
)
raise ValueError(
"custom_prompt is not supported when session_id is provided in API mode"
)
# Session mode: POST a JSON QAEntry so the backend receives
# real text, not a multipart-file placeholder that triggers
# the _SESSION_PLACEHOLDER_PREFIXES skip in _add_to_session.
endpoint = f"{self.api_url}/api/v1/remember/entry"
payload = {
"entry": {
"type": "qa",
"question": "",
"answer": str(data),
"context": "",
},
"dataset_name": dataset_name,
"session_id": session_id,
}
response = await self.client.post(
endpoint,
json=payload,
headers=self._get_headers(),
)
response.raise_for_status()
return response.json()
endpoint = f"{self.api_url}/api/v1/remember"
files = self._text_upload(data)
form_data = {"datasetName": dataset_name}
if custom_prompt:
form_data["custom_prompt"] = custom_prompt
response = await self.client.post(
endpoint,
files=files,
data=form_data,
headers=self._get_headers(include_content_type=False),
)
response.raise_for_status()
return response.json()
else:
with redirect_stdout(sys.stderr):
kwargs = {
"data": data,
"dataset_name": dataset_name,
}
if session_id:
kwargs["session_id"] = session_id
if custom_prompt:
kwargs["custom_prompt"] = custom_prompt
result = await self.cognee.remember(**kwargs)
return {
"status": getattr(result, "status", "completed"),
"dataset_name": dataset_name,
"session_id": session_id,
}
async def recall(
self,
query_text: str,
search_type: Optional[str] = None,
datasets: Optional[List[str]] = None,
session_id: Optional[str] = None,
top_k: int = 15,
) -> Any:
"""Search memory via recall() with auto-routing and session awareness."""
if self.use_api:
endpoint = f"{self.api_url}/api/v1/recall"
payload = {"query": query_text, "top_k": top_k, "search_type": None}
if search_type:
payload["search_type"] = search_type.upper()
if datasets:
payload["datasets"] = datasets
if session_id:
payload["session_id"] = session_id
response = await self.client.post(endpoint, json=payload, headers=self._get_headers())
response.raise_for_status()
return response.json()
else:
with redirect_stdout(sys.stderr):
kwargs = {"top_k": top_k, "auto_route": True}
if search_type:
from cognee.modules.search.types import SearchType
kwargs["query_type"] = SearchType[search_type.upper()]
if datasets:
kwargs["datasets"] = datasets
if session_id:
kwargs["session_id"] = session_id
return await self.cognee.recall(query_text=query_text, **kwargs)
async def forget(
self,
dataset: Optional[str] = None,
data_id: Optional[UUID] = None,
dataset_id: Optional[UUID] = None,
everything: bool = False,
memory_only: bool = False,
) -> Dict[str, Any]:
"""Delete data via forget().
Bug fix (kb#70): this method previously dropped `data_id`,
`dataset_id`, and `memory_only` on the floor, so entry-level
deletion was impossible through the MCP surface even though the
cognee API's /api/v1/forget endpoint has always supported it
(dataset/datasetId + dataId). Forward all fields it accepts.
"""
if self.use_api:
endpoint = f"{self.api_url}/api/v1/forget"
payload = {"everything": everything, "memory_only": memory_only}
if dataset:
payload["dataset"] = dataset
if dataset_id:
payload["dataset_id"] = str(dataset_id)
if data_id:
payload["data_id"] = str(data_id)
response = await self.client.post(endpoint, json=payload, headers=self._get_headers())
response.raise_for_status()
return response.json()
else:
with redirect_stdout(sys.stderr):
return await self.cognee.forget(
dataset=dataset,
dataset_id=dataset_id,
data_id=data_id,
everything=everything,
memory_only=memory_only,
)
async def improve(
self,
dataset_name: str = "main_dataset",
session_ids: Optional[List[str]] = None,
) -> Dict[str, Any]:
"""Enrich knowledge graph and bridge session data via improve()."""
if self.use_api:
endpoint = f"{self.api_url}/api/v1/improve"
payload = {"dataset_name": dataset_name}
if session_ids:
payload["session_ids"] = session_ids
response = await self.client.post(endpoint, json=payload, headers=self._get_headers())
response.raise_for_status()
return response.json()
else:
with redirect_stdout(sys.stderr):
kwargs = {"dataset": dataset_name}
if session_ids:
kwargs["session_ids"] = session_ids
result = await self.cognee.improve(**kwargs)
return {"status": "success", "result": str(result)}
async def close(self):
"""Close the HTTP client if in API mode."""
if self.use_api and hasattr(self, "client"):
await self.client.aclose()

2071
openai/cognee-mcp/src/server.py Normal file
View File

File diff suppressed because it is too large Load Diff